LinkedBoost

Hosted LinkedIn MCP server for AI assistants, with 50 documented tools for connected-seat search, lead imports, reviewed outreach sequences and inbox work.

Hosted MCP Server

npx add-mcp 'https://mcp.linkedboost.ai/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

The LinkedIn MCP server

A LinkedIn MCP server exposes your connected seat as tools Claude can call. LinkedBoost documents 50 of them: search and import leads, inspect history, prepare sequences, comment on known posts, and work an existing inbox thread. An operator reviews external actions, and the server applies account-level limits. Check completion after a tool queues an action.

What is an MCP server, in one paragraph

Model Context Protocol is an open standard for connecting an AI assistant to an outside system. The assistant discovers a list of typed tools, decides which to call, and passes structured arguments. It is the difference between an assistant that knows about LinkedIn and one that can ask a connected tool for an account-scoped operation. Different servers expose different reads and writes; the tool list and its approval behavior matter more than the MCP label.

What your agent can do once connected

Search & organizeSearch through your connected seat, import an authorized CSV, and inspect saved lead groups.
SequencesPrepare a multi-step sequence and review its enrolled people and drafts before external action.
InboxRead an existing thread, inspect its history, and prepare a reply for review.
PacingThe server documents per-seat invitation caps and warm-up behavior; check your seat's current headroom.
Account riskLinkedIn prohibits unauthorized automation. Approval and caps do not eliminate restriction risk.

The tool surface, by the numbers

50 typed tools across 7 areas, every one documented with what it does and what you'd say to Claude to use it.

Every tool, by name

The documented tool surface, with an example of what you would say to Claude. A listed tool is not evidence that an action completed on LinkedIn.

Sourcing runs through your own seat and your own CSV imports. There is no shadow database and no bought lists. Content tools cover commenting and reacting on other people's posts; publishing your own posts is not part of this build.

What you actually say

You type sentences. The agent picks the tools.

  • Import this CSV as a lead group and tell me who I have already spoken to.
  • Search my LinkedIn for second-degree DTC founders in New York who posted this week.
  • Pull their profiles and latest posts, then comment on the three where I have something real to say.
  • Draft a three-step sequence from my seat and show me every draft before anything sends.
  • What went out this week, what is queued, and which sequence is underperforming?
  • How much headroom does my seat have left today?

Setup in 3 steps

  1. 1 · Add the connector. In Claude: Settings → Connectors → Add custom connector: or use the one-click link. Full walkthrough on the connect guide.
  2. 2 · Connect your LinkedIn. One secure flow. Your seat gets a pacing profile and, if it's fresh, a warm-up ramp.
  3. 3 · Talk to Claude. “Find 40 DTC founders in New York who posted this week, draft invites in my voice, queue at safe pace.” Review the queue. Approve.

Where the MCP server fits

The hosted endpoint connects Claude to your LinkedBoost workspace. The account connection, approval decision, server limits, and final action state remain distinct. Other vendors also offer MCP or assistant workflows; the protocol itself does not reduce LinkedIn's terms-of-service risk. See the methodology.

The limits, stated

Invitations per day20Enforced server-side, not a settings field
Invitations per week80Our enforced number. LinkedIn publishes none
Warm-up rampAutomaticAdvances on acceptance rate, not the calendar
Messages to existing connectionsNot invite-cappedThey do not consume invitation quota
Sends metered by usNoSourcing uses credits; check the current plan terms

LinkedIn publishes no invitation limit at all, daily or weekly. The 100 a week you have read elsewhere is not their figure. Ours is a policy we can defend, enforced server side, and it is a product control rather than LinkedIn approval or any guarantee against restriction. The full numbers.

Which agents can connect

Claude (claude.ai and Desktop)Documented setupAdd as a custom connector
Claude Code (terminal)MCP-compatibleCheck your client setup
Other MCP-capable clientsProtocol-compatible in principleEnd-to-end setup not verified here

Questions

Is there an official LinkedIn MCP server?

LinkedIn doesn't publish one. LinkedBoost connects your own account through a managed integration with enforced safety limits: you stay in control of every send.

Which agents work with it?

The setup guide covers Claude. Other MCP clients may be protocol-compatible, but their end-to-end setup has not been verified here.

What's the MCP server URL?

The hosted endpoint is https://mcp.linkedboost.ai/mcp. Sign in through the connector to use your workspace.

Can it get my account restricted?

Yes. LinkedIn prohibits unauthorized automation, and limits or review do not remove account risk. Our restriction rate is still measuring; see /safety for the proposed methodology.

How is this different from a LinkedIn scraper?

It exposes account-scoped write tools as well as search and read tools, including invitations, messages, replies, and comments. A tool listing or queued action is not proof that the action completed.

Do I need Sales Navigator?

No. Search runs through whatever entitlement your seat already has. Sales Navigator gives better filters and InMail credits, but it does not raise the invitation limit and it is not required to connect.

Where do the leads come from?

Your connected LinkedIn seat and CSV data you are authorized to import. There is no bundled contact database or native CRM sync. Check imported history and suppression state before outreach.

Can it post content for me?

It can comment on and react to other people's posts, which is the engagement half of content. Publishing your own posts is a separate capability and is not in this build.

Does it send anything without asking me?

Creating a sequence sends nothing. Enrollment and external actions are documented as reviewed steps. Inspect the queue and final action status in your workspace; do not infer completion from a draft.

What happens when I hit the cap?

The agent is refused. It reports the remaining headroom instead of sending, and the counter frees as the rolling window moves. You cannot override it in the moment, which is the point.

Go deeper

[

What a LinkedIn AI agent can actually run for you

The capability map, tool by tool, and where the agent is deliberately not in charge.

](https://linkedboost.ai/blog/linkedin-ai-agent)[

What actually gets a LinkedIn account restricted

The behavioral signals that carry weight, and what each restriction tier means.

](https://linkedboost.ai/blog/linkedin-automation-ban)

Run it yourself

[

LinkedIn lead generation, run by your agent

The sentences, the tools, the numbers that govern it.

](https://linkedboost.ai/use-cases/lead-generation)[

Warm the room before the invitation lands

Commenting and reacting cost no invitation quota.

](https://linkedboost.ai/use-cases/post-engagement)